Yizhi Song

6 papers · 2023–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

CVPR (2) AAAI (1) ECCV (1) ICLR (1) WACV (1)

Top co-authors

Zhifei Zhang (4) Jianming Zhang (4) Soo Ye Kim (4) Zhe Lin (4) Daniel Aliaga (4) Liu He (3) Scott Cohen (3) He Zhang (2) Wei Xiong (2) Brian Price (2)

Research topics

Computer Vision (4) Generation (4) Processing (4) Deep Learning (3) Models (3) Learning Types · Deep Learning (2) Artificial Intelligence (1) Machine Learning (1) Natural Language Processing (1) Core AI (1) Learning Types · Machine Learning (1) Resources & Methods (1)

Keywords

diffusion model (3) image generation (3) object compositing (2) generative model (2) multimodal learning (1) conditional generation (1) image editing (1) object tracking (1) image harmonization (1) semantic alignment (1) vision-language model (1) multimodal large language model (1) visual instruction tuning (1) temporal coherence (1) identity preservation (1) shape guidance (1) generative object compositing (1) detail preservation (1) diffusion-based image generation (1) 3d visual instruction dataset (1)

Papers

Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation WACV 2026 Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting AAAI 2026 Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment ICLR 2025 IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation CVPR 2024 Thinking Outside the BBox: Unconstrained Generative Object Compositing ECCV 2024 ObjectStitch: Object Compositing With Diffusion Model CVPR 2023